Metraipolis › archive › dc_f1900f677091

OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization — arXiv:2609.10055

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10055
License (as archived)
CC0-1.0
Archived
2026-10-16T07:24:37.192Z
SHA-256 of the archived text
1437c2d6d95e93062bfeb0c8b6c66c57081110a1411307d8e43431e8ca9e6ced
Stable URL of this page
https://metraipolis.com/documento/dc_f1900f677091

How to cite

OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization — arXiv:2609.10055 — arXiv (en), https://arxiv.org/abs/2609.10055 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1900f677091 (Metraipolis archive dc_f1900f677091, sha256 1437c2d6d95e93062bfeb0c8b6c66c57081110a1411307d8e43431e8ca9e6ced)
BibTeX
@misc{dcf1900f677091,
  title = {OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization — arXiv:2609.10055},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10055},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1900f677091; sha256 1437c2d6d95e93062bfeb0c8b6c66c57081110a1411307d8e43431e8ca9e6ced},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10055. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data. This task remains challenging because lexical variation and subtle distinctions among hierarchically related concepts can obscure concept boundaries. We present OntologyAligner, a three-stage framework that combines ontology-aligned retrieval, large language model candidate reranking, and selective hierarchy-guided refinement. We also construct PhenoNormBench, a unified benchmark comprising 13,390 samples from seven Human Phenotype Ontology datasets. OntologyAligner achieved state-of-the-art performance on HPO normalization, with 88.78% Macro Top-1 Accuracy and 86.75% Micro Top-1 Accuracy, exceeding the strongest baseline by 4.85 and 5.07 percentage points, respectively. Ablation analyses showed complementary contributions from all three stages, and sensitivity analyses demonstrated stability across candidate-set sizes and model backbones. Applications to MONDO, MEDIC, and NCBITaxon further established portability to other ontologies. OntologyAligner offers a generalizable framework for accurate mapping of biomedical text to structured ontology concepts. PhenoNormBench and the code are publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.10055 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T07:00:16.236Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).